mirror of
https://github.com/gsi-upm/sitc
synced 2025-08-24 10:32:20 +00:00
Added preprocessing notebooks
This commit is contained in:
committed by
GitHub
parent
1a3f618995
commit
86114b4a56
619
ml21/preprocessing/9_String_Data.ipynb
Normal file
619
ml21/preprocessing/9_String_Data.ipynb
Normal file
@@ -0,0 +1,619 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "skip"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "skip"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# Course Notes for Learning Intelligent Systems"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "skip"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"Department of Telematic Engineering Systems, Universidad Politécnica de Madrid, © Carlos A. Iglesias"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "skip"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## [Introduction to Preprocessing](00_Intro_Preprocessing.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# String Data\n",
|
||||
"It is common to clean string columns so that they follow a predefined format (e.g. emails, URLs, ...).\n",
|
||||
"\n",
|
||||
"We can do it using regular expressions or specific libraries."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Beautifier\n",
|
||||
"Simple [library](https://github.com/labtocat/beautifier) to cleanup and prettify url patterns, domains and so on. Library helps to clean unicodes, special characters and unnecessary redirection patterns from the urls and gives you clean date.\n",
|
||||
"\n",
|
||||
"Install with **'pip install beautifier'**."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Email cleanup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from beautifier import Email\n",
|
||||
"email = Email('me@imsach.in')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'imsach.in'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email.domain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'me'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email.username"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"False"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email.is_free_email"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"email2 = Email('This my address')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"False"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email2.is_valid"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"email3 = Email('pepe@gmail.com')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email3.is_valid"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
]
|
||||
},
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"email3.is_free_email"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## URL cleanup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from beautifier import Url\n",
|
||||
"url = Url('https://in.linkedin.com/in/sachinphilip?authtoken=887nasdadasd6hasdtg21&secret=98jy766yhhuhnjk')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'https://in.linkedin.com/in/sachinphilip'"
|
||||
]
|
||||
},
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url.cleanup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'in.linkedin.com'"
|
||||
]
|
||||
},
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url.domain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['authtoken=887nasdadasd6hasdtg21', 'secret=98jy766yhhuhnjk']"
|
||||
]
|
||||
},
|
||||
"execution_count": 35,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url.param"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 37,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'authtoken=887nasdadasd6hasdtg21&secret=98jy766yhhuhnjk'"
|
||||
]
|
||||
},
|
||||
"execution_count": 37,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url.parameters"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'sachinphilip'"
|
||||
]
|
||||
},
|
||||
"execution_count": 39,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url.username"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Unicode\n",
|
||||
"Problem: Some unicode code has been broken. We see the character in a different character dataset.\n",
|
||||
"\n",
|
||||
"A **mojibake** is a character displayed in an unintended character enconding. Example: \"<22>\").\n",
|
||||
"\n",
|
||||
"We will use the library **ftfy** (fixed text for you) to fix it.\n",
|
||||
"\n",
|
||||
"First, you should install the library: ***conda install ftfy**. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"¯\\_(ツ)_/¯\n",
|
||||
"Party\n",
|
||||
"I'm\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import ftfy\n",
|
||||
"foo = '¯\\\\_(ã\\x83\\x84)_/¯'\n",
|
||||
"bar = '\\ufeffParty'\n",
|
||||
"baz = '\\001\\033[36;44mI’m'\n",
|
||||
"print(ftfy.fix_text(foo))\n",
|
||||
"print(ftfy.fix_text(bar))\n",
|
||||
"print(ftfy.fix_text(baz))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "subslide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"We can understand which heuristics ftfy is using."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "NameError",
|
||||
"evalue": "name 'ftfy' is not defined",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
|
||||
"\u001b[0;32m<ipython-input-1-4030b963ff0a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mftfy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexplain_unicode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfoo\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
|
||||
"\u001b[0;31mNameError\u001b[0m: name 'ftfy' is not defined"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ftfy.explain_unicode(foo)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "slide"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Dates\n",
|
||||
"Sometimes we want to extract date from text. We can use regular expressions or handy packages, such as **python-dateutil**.\n",
|
||||
"\n",
|
||||
"Install the library: **pip install python-dateutil**."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "fragment"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2019-08-22 10:22:46+00:00\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from dateutil.parser import parse\n",
|
||||
"now = parse(\"Thu Aug 22 10:22:46 UTC 2019\")\n",
|
||||
"print(now)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2019-08-22 10:20:00\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"dt = parse(\"Today is Thursday 8, 2019 at 10:20:00AM\", fuzzy=True)\n",
|
||||
"print(dt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"slideshow": {
|
||||
"slide_type": "skip"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# References\n",
|
||||
"* [Cleaning and Prepping Data with Python for Data Science — Best Practices and Helpful Packages](https://medium.com/@rrfd/cleaning-and-prepping-data-with-python-for-data-science-best-practices-and-helpful-packages-af1edfbe2a3), DeFilippi, 2019, \n",
|
||||
"* [Data Preprocessing for Machine learning in Python, GeeksForGeeks](https://www.geeksforgeeks.org/data-preprocessing-machine-learning-python/)\n",
|
||||
"* Beautifier https://github.com/labtocat/beautifier\n",
|
||||
"* Ftfy https://ftfy.readthedocs.io/en/latest/\n",
|
||||
"* python-dateutil https://dateutil.readthedocs.io/en/stable/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Licence\n",
|
||||
"The notebook is freely licensed under under the [Creative Commons Attribution Share-Alike license](https://creativecommons.org/licenses/by/2.0/). \n",
|
||||
"\n",
|
||||
"© Carlos A. Iglesias, Universidad Politécnica de Madrid."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"celltoolbar": "Slideshow",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.4"
|
||||
},
|
||||
"latex_envs": {
|
||||
"LaTeX_envs_menu_present": true,
|
||||
"autocomplete": true,
|
||||
"bibliofile": "biblio.bib",
|
||||
"cite_by": "apalike",
|
||||
"current_citInitial": 1,
|
||||
"eqLabelWithNumbers": true,
|
||||
"eqNumInitial": 1,
|
||||
"hotkeys": {
|
||||
"equation": "Ctrl-E",
|
||||
"itemize": "Ctrl-I"
|
||||
},
|
||||
"labels_anchors": false,
|
||||
"latex_user_defs": false,
|
||||
"report_style_numbering": false,
|
||||
"user_envs_cfg": false
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 1
|
||||
}
|
Reference in New Issue
Block a user